Theory-driven neural network for total organic carbon content estimation from well logs

Total organic carbon content (TOC) is a crucial geochemical indicator for assessing the hydrocarbon generation potential of source rock formations. Traditional TOC evaluation methods employing well logs do not match well with measured data in complex formations. While intelligent algorithms have the potential to improve TOC estimation accuracy, they have poor petrophysical significance. In this study, we develop the theory-driven neural networks (TdNN) to extend TOC prediction accuracy via combining logging mechanism models into the input of a neural network. TdNN have two ways of merging petrophysical models with an intelligent model, specifically TdNN based on series connection (STdNN) and on embedding (ETdNN). STdNN processes log responses through logging mechanism models and subsequently inputs them to the neural network for TOC evaluation. ETdNN inputs log responses and calculation results from logging mechanism models to the neural network to estimate TOC. These two ways achieve more accurate prediction results than an ordinary neural network by improving the quality of input data, analogous to applying data augmentation methods on intelligent models. This study uses the Schmoker method, delta logR method, and multivariate regression as logging mechanism models of TdNN. The prediction performance of the proposed models is tested using data from two shale reservoirs in the Longmaxi Formation and the Shahejie Formation. Results show that the proposed ETdNN achieves the highest prediction accuracy, meaning that the ETdNN is suitable for predicting TOC of shale formations.